Subunit Nonresponse in the National Health Interview Survey (NHIS): An Exploration Using Paradata

• Activity Number: 6
• Type: Invited
• Date/Time: Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
• Sponsor: Section on Government Statistics
• Author(s): James M. Dahlhamer*+ and Catherine M. Simile
• Companies: National Center for Health Statistics and National Center for Health Statistics
• Keywords: paradata ; subunit nonresponse ; nonresponse bias ; survey participation

Abstract

The NHIS interview protocol includes a household interview, a family interview (for each family in a household), and subunit interviews (within each family) with a randomly selected adult 18 or older (sample adult) and about a randomly selected child under the age of 18. While the household and family response rates remain high (87% in 2007), the sample adult response rate has dropped to under 70%. Since critical health information is collected from sample adults, more attention should be given to their participation rates and the potential for bias in key health estimates. In this paper, we use paradata, including measures of respondent reluctance, along with frame, family-level, and sample adult data (health and sociodemographic data collected with the family interview), to model sample adult participation and explore bias due to sample adult nonresponse.